Skip to main content

Tieto develops AI-IoT pedestrian recognition 

Tieto and the Finnish city of Tampere have launched a pedestrian recognition system which it claims can achieve up to 99% accuracy - and 75% at night.  
By Ben Spencer February 13, 2020 Read time: 1 min
AI and IoT in action at an intersection (Source: City of Tampere)

The software company says the solution utilises artificial intelligence (AI) and Internet of Things technology to automatically detect when a pedestrian is planning to cross the street at an intersection.

In Tampere, an intersection traffic camera feed was connected to a cloud-based AI system which monitors vehicles and pedestrians. The system sends an alert once its algorithms detect a pedestrian beginning to cross the street. This alert can be relayed to other connected systems and could be relayed directly to vehicles to alert drivers in the future, Tieto adds.  

Pekka Stenman, traffic engineer at the City of Tampere, says: “We want to see how people move, and perhaps construct heat maps of Tampere's pedestrian flows to assist with traffic planning. Another interesting opportunity is introducing more intelligence to traffic lights by identifying and predicting people flows.”
 

Related Content

  • March 10, 2023
    Bridgestone AI gives cities conditional insight
    Two solutions allow authorities to use anonymised data to identify potential problems
  • May 25, 2021
    Waycare uses AI to manage Texas traffic
    Waycare system also employs machine learning to alert traffic managers to potential hazards
  • June 4, 2015
    Greenowl brings bespoke traveller information one step closer
    Greenowl’s voice-only congestion warning smartphone app alerts drivers to problems ahead and could be the way ahead for traffic information. If there is one point Matt Man, CEO of Canadian company Greenowl, wants to make clear from the start, it is that his company’s app is not a navigation system. He says: “Our system does not direct drivers to their destination because we mainly focus on commuters who know how to get to where they are going and only need information about any delays and incidents ahead of
  • September 4, 2018
    Getting to the point
    Cars are starting to learn to understand the language of pointing – something that our closest relative, the chimpanzee, cannot do. And such image recognition technology has profound mobility implications, says Nils Lenke Pointing at objects – be it with language, using gaze, gestures or eyes only – is a very human ability. However, recent advances in technology have enabled smart, multimodal assistants - including those found in cars - to action similar pointing capabilities and replicate these human qual